Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 328 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2699. Min Act: -0.0003

Data Index: 76213 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2505. Min Act: -0.0003

Data Index: 524720 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2433. Min Act: -0.0003

Data Index: 534043 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2325. Min Act: -0.0003

Data Index: 386207 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2500. Min Act: -0.0003

Data Index: 65358 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1925. Min Act: -0.0003

Data Index: 930704 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2239. Min Act: -0.0003

Data Index: 493284 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1981. Min Act: -0.0003

Data Index: 333077 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.2125. Min Act: -0.0003

Data Index: 1137049 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1998. Min Act: -0.0003

Data Index: 1240666 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1914. Min Act: -0.0003

Data Index: 599073 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1947. Min Act: -0.0003

Data Index: 1243041 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1878. Min Act: -0.0003

Data Index: 744209 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1704. Min Act: -0.0003

Data Index: 229076 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1657. Min Act: -0.0003

Data Index: 766868 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1634. Min Act: -0.0003

Data Index: 1195602 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1373. Min Act: -0.0003

Data Index: 917615 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1512. Min Act: -0.0003

Data Index: 181341 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1417. Min Act: -0.0003

Data Index: 330894 (C4 (Web Text))

Max Activating Token Index: 352

Text #19

Max Range: 0.2699. Min Range: -0.2699

Max Act: 0.1371. Min Act: -0.0003

Data Index: 261317 (C4 (Web Text))

Max Activating Token Index: 639